Plugins / Citing & writing

Document Parser for Zotero

by Jiahaohong · github.com/Jiahaohong/mineru-to-zotero

Parses PDFs into Markdown from a right-click menu using MinerU, markitdown, docling, vision OCR, Baidu OCR, TextIn or Doc2X.

Document Parser for Zotero has a Zotero Plugins grade of B (use with care) because it launches programs on your computer. It works with Zotero 7–9, not the current Zotero 10. Last checked 15 Nov 2026.

View source
Downloads a .xpi file (0.05 MB). In Zotero, open Tools → Plugins and install it from the file.
In useAn estimate of how many copies of Zotero have it: Zotero downloads each new version once for every copy that has the plugin, so we count the downloads of its most-downloaded recent release. Rounded. Plugins that update from outside GitHub count low.
190
DownloadsAll-time downloads of its release files from GitHub, counting every update. Installs from elsewhere aren't counted.
215
Latest releaseDownloads of version 0.1.24, its latest release, since it came out on 17 Aug 2026. A new release starts from zero; Downloads counts every release.
183
ReleasesVersions published on GitHub. Everyone who has the plugin downloads each one again, which adds up in Downloads.
5
AgeTime since its GitHub repository was created, on 15 Aug 2026. The plugin can be younger than its repository.
3 months
StarsPeople who starred the repository on GitHub: a rough measure of interest.
1
ContributorsPeople who have committed code to this plugin. Bots don't count, nor do the authors of a template or project it was copied from.
1
LicenceThe licence the code is published under, as GitHub reports it.
MIT
B
Zotero Plugins gradeUse with care
because it launches programs on your computer
Applies to v0.1.24, released 17 Aug 2026Code checked · in Zotero 9.0.6 on 27 Sep 2026 it did something its card didn't describe
Doesn't work with the current Zotero (10)Works with Zotero 7, 8, 9.
Documentation in Chinese onlyOur summary is in English, but the plugin's own docs and support are in Chinese.
What we found in the codeSets the gradeThe worst finding in these three areas sets the grade.
Code transparencyReadable code; not yet checked against the published sourceThe developer uploaded the release file from the Jiahaohong account. We haven't yet checked whether this file matches the public source code.UnknownWe couldn't check this yet.
Updates
Updates come from this project's GitHub repositoryThe update address offers version 0.1.24, which isn't newer than this one, so Zotero won't update it for now
Where your data goesOnly contacts services we could identify6 addresses in 2 groups.LowLow concern: normal for plugins that do this job. Listed so you know.
AI services (4)
aip.baidubce.comapi.openai.comapi.textin.comv2.doc2x.noedgeai.com
Apps you connect (2)
mineru.netseen when we ran itIt contacted this address when we ran it in Zotero.mineru.oss-cn-shanghai.aliyuncs.comseen when we ran itIt contacted this address when we ran it in Zotero.
Where we found it
aip.baidubce.comdocument-parser.js · line 790
let url = "https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials"
api.openai.comdocument-parser.js · line 61
visionBaseURL: String(this.getPref("visionBaseURL", "https://api.openai.com/v1")).trim().replace(/\/+$/, ""),
api.textin.comdocument-parser.js · line 842
"https://api.textin.com/ai/service/v1/pdf_to_markdown?get_image=none&markdown_details=0&table_flavor=md",
Powerful capabilitiesLaunches programs on your computer, and 2 moreMediumMedium concern: worth reading before you install. One medium finding makes the grade B.
Medium concern (1)
Launches programs on your computer
Low concern (2)
Stores API keys or passwordsWorks with files on your computer
Where we found it
Launches programs on your computerdocument-parser.js · line 680
let { Subprocess } = ChromeUtils.importESModule("resource://gre/modules/Subprocess.sys.mjs");
Before you installShown, not gradedFacts to help you decide. They don't change the grade.
Works withZotero 7, 8, 9 · not 10Doesn't work with the current Zotero (10)MediumMedium concern: worth reading before you install. One medium finding makes the grade B.
Zotero 7 ✓ worksZotero 8 ✓ worksZotero 9 ✓ worksZotero 10 ✗ doesn't workZotero 11 beta not tested yet: Zotero hasn't opened Zotero 11 testing
What you'll needAn API key for some featuresDetected automatically from its code
No further detail for this area yet.
MaintenanceActive · last release 17 Aug 20261 contributor
No further detail for this area yet.
LanguagesDocumentation in Chinese onlyInterface: English and Chinese
No further detail for this area yet.
We report what we found in the code. Open any area for the evidence.How we gradeReport a problem

What it does

Written by AI from the README

Parses PDFs into Markdown from a right-click menu using MinerU, markitdown, docling, vision OCR, Baidu OCR, TextIn or Doc2X. It carries your PDF highlights into the Markdown with their colours. Can also export a highlights-only file with the PDF outline.

Getting readable Markdown out of PDFs, with your highlights intact, is useful for notes and LLM workflows. Some backends need your own API credentials or a local tool.

What you'll need

Detected automatically
  • An API key for some featuresWorks without one: MinerU free Agent API when no token is set (default), or local markitdown/docling CLIs. Needs a key (MinerU, OpenAI-compatible vision API, Baidu AI Cloud, TextIn and Doc2X): MinerU Precision API token, vision LLM OCR, Baidu OCR, TextIn, Doc2X.
  • Zotero 7, 8, 9Not working with Zotero 10

Where your data goes

We found: only contacts services we could identify. 6 addresses in 2 groups.

AI services (4)
aip.baidubce.comapi.openai.comapi.textin.comv2.doc2x.noedgeai.com
Apps you connect (2)
mineru.netseen when we ran itmineru.oss-cn-shanghai.aliyuncs.comseen when we ran it
Evidence · file and line
aip.baidubce.comdocument-parser.js · line 790
let url = "https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials"
api.openai.comdocument-parser.js · line 61
visionBaseURL: String(this.getPref("visionBaseURL", "https://api.openai.com/v1")).trim().replace(/\/+$/, ""),
api.textin.comdocument-parser.js · line 842
"https://api.textin.com/ai/service/v1/pdf_to_markdown?get_image=none&markdown_details=0&table_flavor=md",

Other plugins that do this

Matched on what they do

For the same job, work with Zotero 10 and graded B or better. Closest match first.

  • B
    Mineru Parse

    Converts PDF attachments into structured Zotero notes using the MinerU cloud service, extracting text, formulas, tables and images.

    Matches “mineru pdf parsing” · 115 downloads · Active · Zotero 7–10
    Works with Zotero 10
  • A
    zotero-docling

    Converts PDF attachments to structured Markdown using a local docling-serve server and attaches the .md file to the same item.

    Matches “ocr pdf to markdown” · 1,467 downloads · Active · Zotero 8–10
    Works with Zotero 10
Compare all 3 side by side
How we pick these

By how closely what they do matches this plugin, using descriptions and the phrases people search with. Copies and forks of this plugin are listed under Forks and copies instead. No plugin pays to appear here.

Forks and copies

No forks listed.

The developer's response

The developer hasn't responded. Developers can reply here, and their reply sits next to our findings.I'm the developer

Ratings and reviews

What people who use it say. This is separate from the grade, which is what the code does, and never changes it.

No ratings yet.

Write a review
Your rating of Document Parser for Zotero v0.1.24

Your review is public, under the name you give, and published with the directory's data under CC BY 4.0. Links are removed. We never store your IP address: a scrambled code made from it is kept for 30 days to catch fake reviews. Every review is checked before it's published; how fake ones are spotted isn't published, so it can't be gamed.

Install Document Parser for Zotero
BUse with care
Before you install: It launches programs on your computer.Read the finding
Compare with similar plugins